mirror of
https://github.com/puppetlabs/vmpooler.git
synced 2026-01-25 17:48:41 -05:00
b3be210f99
- Implement dead-letter queue (DLQ) to capture failed VM operations - Implement auto-purge to clean up stale queue entries - Implement health checks to monitor queue health - Add comprehensive tests and documentation Features: - DLQ captures failures from pending, clone, and ready queues - Auto-purge removes stale VMs with configurable thresholds - Health checks expose metrics for monitoring and alerting - All features opt-in via configuration (backward compatible)
92 lines
3.1 KiB
Text
92 lines
3.1 KiB
Text
---
|
|
# VMPooler Configuration Example with Dead-Letter Queue, Auto-Purge, and Health Checks
|
|
|
|
# Redis Configuration
|
|
:redis:
|
|
server: 'localhost'
|
|
port: 6379
|
|
data_ttl: 168 # hours - how long to keep VM metadata in Redis
|
|
|
|
# Dead-Letter Queue (DLQ) Configuration
|
|
dlq_enabled: true
|
|
dlq_ttl: 168 # hours (7 days) - how long to keep DLQ entries
|
|
dlq_max_entries: 10000 # maximum entries per DLQ queue before trimming
|
|
|
|
# Application Configuration
|
|
:config:
|
|
# ... other existing config ...
|
|
|
|
# Dead-Letter Queue (DLQ) - Optional, defaults shown
|
|
dlq_enabled: false # Set to true to enable DLQ
|
|
dlq_ttl: 168 # hours (7 days)
|
|
dlq_max_entries: 10000 # per DLQ queue
|
|
|
|
# Auto-Purge Stale Queue Entries
|
|
purge_enabled: false # Set to true to enable auto-purge
|
|
purge_interval: 3600 # seconds (1 hour) - how often to run purge cycle
|
|
purge_dry_run: false # Set to true to log what would be purged without actually purging
|
|
|
|
# Auto-Purge Age Thresholds (in seconds)
|
|
max_pending_age: 7200 # 2 hours - VMs stuck in pending
|
|
max_ready_age: 86400 # 24 hours - VMs idle in ready queue
|
|
max_completed_age: 3600 # 1 hour - VMs in completed queue
|
|
max_orphaned_age: 86400 # 24 hours - orphaned VM metadata
|
|
max_request_age: 86400 # 24 hours - stale on-demand requests
|
|
|
|
# Health Checks
|
|
health_check_enabled: false # Set to true to enable health checks
|
|
health_check_interval: 300 # seconds (5 minutes) - how often to run health checks
|
|
|
|
# Health Check Thresholds
|
|
health_thresholds:
|
|
pending_queue_max: 100 # Warning threshold for pending queue size
|
|
ready_queue_max: 500 # Warning threshold for ready queue size
|
|
dlq_max_warning: 100 # Warning threshold for DLQ size
|
|
dlq_max_critical: 1000 # Critical threshold for DLQ size
|
|
stuck_vm_age_threshold: 7200 # 2 hours - age at which VM is considered "stuck"
|
|
stuck_vm_max_warning: 10 # Warning threshold for stuck VM count
|
|
stuck_vm_max_critical: 50 # Critical threshold for stuck VM count
|
|
|
|
# Pool Configuration
|
|
:pools:
|
|
- name: 'centos-7-x86_64'
|
|
size: 5
|
|
provider: 'vsphere'
|
|
# ... other pool settings ...
|
|
|
|
# Provider Configuration
|
|
:providers:
|
|
:vsphere:
|
|
server: 'vcenter.example.com'
|
|
username: 'vmpooler'
|
|
password: 'secret'
|
|
# ... other provider settings ...
|
|
|
|
# Example: Production Configuration
|
|
# For production use, you might want:
|
|
# :config:
|
|
# dlq_enabled: true
|
|
# dlq_ttl: 168 # Keep failed VMs for a week
|
|
#
|
|
# purge_enabled: true
|
|
# purge_interval: 1800 # Run every 30 minutes
|
|
# purge_dry_run: false
|
|
# max_pending_age: 3600 # Purge pending VMs after 1 hour
|
|
# max_ready_age: 172800 # Purge ready VMs after 2 days
|
|
#
|
|
# health_check_enabled: true
|
|
# health_check_interval: 300 # Check every 5 minutes
|
|
|
|
# Example: Development Configuration
|
|
# For development/testing, you might want:
|
|
# :config:
|
|
# dlq_enabled: true
|
|
# dlq_ttl: 24 # Keep failed VMs for a day
|
|
#
|
|
# purge_enabled: true
|
|
# purge_interval: 600 # Run every 10 minutes
|
|
# purge_dry_run: true # Test mode - log but don't actually purge
|
|
# max_pending_age: 1800 # More aggressive - 30 minutes
|
|
#
|
|
# health_check_enabled: true
|
|
# health_check_interval: 60 # Check every minute
|